Nonlinear shape normalization methods for the recognition of large-set handwritten characters

Seong Whan Lee, Jeong Seon Park

Research output: Contribution to journalArticle

78 Citations (Scopus)

Abstract

Recently, several nonlinear shape normalization methods have been proposed in order to compensate for shape distortions in large-set handwritten characters. In this paper, these methods are reviewed from the two points of view: feature projection and feature density equalization. The former makes feature projection histogram by projecting a certain feature at each point onto horizontal- or vertical-axis and the latter equalizes the feature densities of input image by re-sampling the feature projection histogram. Then, the results of quantitative evaluation for these methods are presented. These methods have been implemented on a PC in C language and tested with a large variety of handwritten Hangul syllables. A systematic comparison of them has been made based on the following criteria: recognition rate, processing speed, computational complexity and degree of variation.

Original languageEnglish
Pages (from-to)895-902
Number of pages8
JournalPattern Recognition
Volume27
Issue number7
DOIs
Publication statusPublished - 1994 Dec 1
Externally publishedYes

Fingerprint

Character sets
Computational complexity
Sampling
Processing

Keywords

  • Feature density equalization
  • Feature projection
  • Handwritten character recognition
  • Nonlinear shape normalization
  • Performance evaluation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Nonlinear shape normalization methods for the recognition of large-set handwritten characters. / Lee, Seong Whan; Park, Jeong Seon.

In: Pattern Recognition, Vol. 27, No. 7, 01.12.1994, p. 895-902.

Research output: Contribution to journalArticle

@article{c2226a8ad2194d59ada1b13669b5eb8b,
title = "Nonlinear shape normalization methods for the recognition of large-set handwritten characters",
abstract = "Recently, several nonlinear shape normalization methods have been proposed in order to compensate for shape distortions in large-set handwritten characters. In this paper, these methods are reviewed from the two points of view: feature projection and feature density equalization. The former makes feature projection histogram by projecting a certain feature at each point onto horizontal- or vertical-axis and the latter equalizes the feature densities of input image by re-sampling the feature projection histogram. Then, the results of quantitative evaluation for these methods are presented. These methods have been implemented on a PC in C language and tested with a large variety of handwritten Hangul syllables. A systematic comparison of them has been made based on the following criteria: recognition rate, processing speed, computational complexity and degree of variation.",
keywords = "Feature density equalization, Feature projection, Handwritten character recognition, Nonlinear shape normalization, Performance evaluation",
author = "Lee, {Seong Whan} and Park, {Jeong Seon}",
year = "1994",
month = "12",
day = "1",
doi = "10.1016/0031-3203(94)90155-4",
language = "English",
volume = "27",
pages = "895--902",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "7",

}

TY - JOUR

T1 - Nonlinear shape normalization methods for the recognition of large-set handwritten characters

AU - Lee, Seong Whan

AU - Park, Jeong Seon

PY - 1994/12/1

Y1 - 1994/12/1

N2 - Recently, several nonlinear shape normalization methods have been proposed in order to compensate for shape distortions in large-set handwritten characters. In this paper, these methods are reviewed from the two points of view: feature projection and feature density equalization. The former makes feature projection histogram by projecting a certain feature at each point onto horizontal- or vertical-axis and the latter equalizes the feature densities of input image by re-sampling the feature projection histogram. Then, the results of quantitative evaluation for these methods are presented. These methods have been implemented on a PC in C language and tested with a large variety of handwritten Hangul syllables. A systematic comparison of them has been made based on the following criteria: recognition rate, processing speed, computational complexity and degree of variation.

AB - Recently, several nonlinear shape normalization methods have been proposed in order to compensate for shape distortions in large-set handwritten characters. In this paper, these methods are reviewed from the two points of view: feature projection and feature density equalization. The former makes feature projection histogram by projecting a certain feature at each point onto horizontal- or vertical-axis and the latter equalizes the feature densities of input image by re-sampling the feature projection histogram. Then, the results of quantitative evaluation for these methods are presented. These methods have been implemented on a PC in C language and tested with a large variety of handwritten Hangul syllables. A systematic comparison of them has been made based on the following criteria: recognition rate, processing speed, computational complexity and degree of variation.

KW - Feature density equalization

KW - Feature projection

KW - Handwritten character recognition

KW - Nonlinear shape normalization

KW - Performance evaluation

UR - http://www.scopus.com/inward/record.url?scp=0028467868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028467868&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(94)90155-4

DO - 10.1016/0031-3203(94)90155-4

M3 - Article

AN - SCOPUS:0028467868

VL - 27

SP - 895

EP - 902

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 7

ER -